Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Abnormal anchor identification method, storage medium and terminal of live broadcast platform

A live broadcast platform and identification method technology, applied in the Internet field, can solve problems such as inability to realize rapid identification, and achieve the effect of maintaining operation order, high accuracy, and less calculation

Active Publication Date: 2019-08-30
GUANGZHOU HUYA INFORMATION TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the above technical problems, especially the problem that the existing technology cannot quickly identify the abnormal anchors who hire network trolls to post barrage, so as to maintain the operation order of the live broadcast platform, the following technical solutions are proposed:

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Abnormal anchor identification method, storage medium and terminal of live broadcast platform
  • Abnormal anchor identification method, storage medium and terminal of live broadcast platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Embodiments of the present invention provide a method for identifying abnormal hosts on a live broadcast platform, such as figure 1 As shown, the method includes:

[0042] Step S101: Obtain the live broadcast data of the anchors of the live broadcast platform; select the anchors to be detected from the anchors of the live broadcast platform according to the live broadcast data.

[0043] In the field of online live broadcasting, the number of bullet screens a host broadcasts during a live broadcast is one of the important reference indicators reflecting the popularity of the live broadcast of the anchor.

[0044] For this embodiment, the identification of the abnormal anchor is mainly aimed at the anchor who has the behavior of hiring network trolls to generate barrage during the live broadcast. number to increase their popularity on the live broadcast platform. Among the popular anchors on the live broadcast platform, there may be such abnormal anchors who increase th...

Embodiment 2

[0064] Another possible implementation of the embodiment of the present invention, on the basis of the first embodiment, further includes the steps shown in the second embodiment, wherein,

[0065] The live broadcast data includes the duration of the barrage;

[0066] According to the live broadcast data, before selecting the anchor to be detected from the anchors of the live broadcast platform, it also includes: selecting the duration of the bullet chat from the live broadcast platform according to the duration of the bullet chat in the live broadcast data Hosts greater than the preset threshold are regarded as effective hosts on the platform;

[0067] The selecting an anchor to be detected from anchors on the live broadcast platform according to the live data includes: selecting an anchor to be detected from effective anchors on the live platform according to the live data.

[0068] For this embodiment, the bullet chat duration is the length of time the host obtains the bul...

Embodiment 3

[0070] Another possible implementation of the embodiment of the present invention, on the basis of the first embodiment, further includes the steps shown in the third embodiment, wherein,

[0071] After identifying that the anchor to be detected is an abnormal anchor, it also includes:

[0072] Adding abnormal hosts to the list of abnormal hosts; restricting the live broadcast rights of the abnormal hosts in the list of abnormal hosts.

[0073] For this embodiment, when the object of the abnormal anchor identification method of the live broadcast platform is the anchor of the live broadcast site of this station, the behavior data used when calculating the intimacy between the user to be detected and the anchor to be detected is in addition to the present invention In addition to the amount of gifts sent and the number of days of barrage sending described in Embodiment 1, it can also be user behavior data that is easily obtained by the live broadcast site of this site, such as ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a method for identifying an abnormal host on a live broadcast platform, the method comprising: acquiring live broadcast data of the hosts on the live broadcast platform; selecting an anchor to be detected from the hosts on the live broadcast platform according to the live broadcast data; acquiring the live broadcast platform to watch The behavior data of the users of the live broadcast of the anchor to be detected includes the amount of bullet chatting; according to the amount of bullet chatting corresponding to the anchor to be detected in the behavior data, among the users who watch the anchor to be detected from the live broadcast platform Selecting the user to be detected; calculating the degree of intimacy between the user to be detected and the anchor to be detected according to the behavior data of the user to be detected; if the intimacy is less than a preset threshold, identifying the anchor to be detected as an abnormal anchor . The method can realize the simple and fast identification of abnormal hosts on the live broadcast platform, and the recognition process requires less calculation and the recognition results are highly accurate, which in turn can provide strong support for maintaining the operation order of the live broadcast platform.

Description

technical field [0001] The present invention relates to the field of Internet technology, in particular, the present invention relates to a method for identifying an abnormal host on a live broadcast platform, a storage medium and a terminal. Background technique [0002] With the development of Internet technology, webcasting has gradually become one of the most popular entertainment methods. On the live broadcast platform, barrage is a way for the host to interact with the audience. The number of barrages the host has during the live broadcast has become an important reference indicator for evaluating whether the anchor is a popular anchor on the platform. For this reason, in order to increase their popularity on the live broadcast platform, many anchors have hired Internet trolls to scan the barrage during their live broadcasts. This kind of online troll behavior has seriously affected the authenticity of the anchor barrage and the operation of the live broadcast platform...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/441H04N21/442H04N21/4788H04N21/488H04N21/431
Inventor 张祥古浩源
Owner GUANGZHOU HUYA INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products